Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 5 of 5 for “"Vision neuroscience"”.

  1. Recurrent neural networks in cognitive and vision neuroscience

    This thesis investigates the development of novel training methodologies for biologically plausible neural networks, with a focus on models that incorporate recurrent dynamics characteristic of cortical circuits. First, we present an innovative approach for training stabilized supralinear networks, …

    cambridge Repository record for Recurrent neural networks in cognitive and vision neuroscience (opens in a new tab)

  2. Light Dance: Beyond the Dichotomy of Light and Vision

    … Light Dance: Beyond the Dichotomy of Light and Vision Seth Riskin This practice-based dissertation focuses on Light Dance, an original artistic practice developed by the author that, in reducing light to its core elements in a setting devoid of other sources of illumination, centers the …

    plymouth Repository record for Light Dance: Beyond the Dichotomy of Light and Vision (opens in a new tab)

  3. Dictionary learning for scalable sparse image representation

    … from experimental sciences, astronomy, computer vision,neuroscience mobile networks etc., are all in constant search for scalable and efficient data processing tools which would enable more effective analysis of continuous video streams containing millions of pixels. Therefore, the question of …

    strathclyde Repository record for Dictionary learning for scalable sparse image representation (opens in a new tab)

  4. Recurrent convolutional neural networks as models of biological object recognition

    Deep feedforward neural network models of vision dominate in both computational neuroscience and engineering. However, the primate visual system contains abundant recurrent connections. In this thesis, we investigate the addition of recurrent connections to the popular framework of convolutional …

    cambridge Repository record for Recurrent convolutional neural networks as models of biological object recognition (opens in a new tab)

  5. High-Throughput Operant Conditioning in Drosophila Larvae

    Operant conditioning is the process by which animals learn to associate their own behaviour with positive or negative outcomes, biasing future action selection in order to maximise reward and avoid punishment. It is an important strategy to ensure survival in an ever-changing environment. Although …

    cambridge Repository record for High-Throughput Operant Conditioning in Drosophila Larvae (opens in a new tab)